## intent:check_balance
- what is my balance <!-- 没有实体 -->
- how much do I have on my [savings](source_account) <!-- 实体source_account的值是savings -->
- how much do I have on my [savings account](source_account:savings) <!-- savings同义词account -->
- Could I pay in [yen](currency)? <!-- 实体通过查询表获取 -->
{
"rasa_nlu_data": {
"common_examples": [], //训练模型的内容放在这里
"regex_features" : [],
"lookup_tables" : [],
"entity_synonyms": []
}
}
language: "zh"
pipeline:
- name: "nlp_mitie"
model: "data/total_word_feature_extractor_zh.dat"
- name: "tokenizer_jieba"
- name: "ner_mitie"
- name: "ner_synonyms"
- name: "intent_entity_featurizer_regex"
- name: "intent_featurizer_mitie"
- name: "intent_classifier_sklearn"
使用 nlu.md 和 nlu_config.yml 训练NLU模型;
python -m rasa_nlu.train -c nlu_config.yml --data nlu.md -o models --fixed_model_name nlu --project current --verbose
;
写剧本,一个剧本是用户和机器人之间真实的对话,用户输入是意图,机器人响应是下一步动作,保存到 stories.md 文件中;
## story_check_balance <!--- 剧本名,可选,调试时有用 -->
* check_balance <!--- 用户的意图和实体 ->
- utter_name <!--- 响应动作 -->
python -m rasa_core.train -d domain.yml -s stories.md -o models/dialogue
2019年04月26号